ad0607f900
### What this PR does / why we need it? This PR introduces the Ascend implementation of the `dispatch_ffn_combine` kernel and wires it into the vLLM-Ascend runtime, together with follow‑up fixes to ensure the kernel builds and runs correctly in CI. - Add full host and device implementation of the `dispatch_ffn_combine` kernel under `csrc/dispatch_ffn_combine`, including tiling logic, MOE routing helpers, and kernel utilities for quantized FFN dispatch. - Integrate the new kernel with the PyTorch binding (csrc/torch_binding.cpp, csrc/torch_binding_meta.cpp) and the Ascend runtime (vllm_ascend/ascend_forward_context.py, vllm_ascend/worker/model_runner_v1.py). - Extend fused MoE communication and token dispatch support in `vllm_ascend/ops/fused_moe`, adding methods/utilities needed by the new dispatch path. - Update quantization logic in vllm_ascend/quantization/w8a8_dynamic.py to support the new FFN dispatch flow. - Fix kernel build issues by adjusting `csrc/build_aclnn.sh`, CMake configuration, and include/namespace usage in the new kernel files. - Add an end‑to‑end nightly test `tests/e2e/nightly/ops/test_dispatch_ffn_combine.py` and helper utilities in `vllm_ascend/utils.py` to validate the new kernel. ### Does this PR introduce _any_ user-facing change? ### How was this patch tested? - vLLM version: v0.12.0 - vLLM main: https://github.com/vllm-project/vllm/commit/v0.12.0 --------- Signed-off-by: mojave2 <chenchen145@huawei.com> Co-authored-by: wangxiyuan <wangxiyuan1007@gmail.com>
25 lines
670 B
C++
25 lines
670 B
C++
#ifndef SELECT_HELPER_HPP
|
|
#define SELECT_HELPER_HPP
|
|
|
|
#include "catlass/layout/layout.hpp"
|
|
using namespace AscendC;
|
|
using namespace Catlass;
|
|
|
|
template <typename Layout, typename ElementType, typename = void>
|
|
struct LayoutBInitializer {
|
|
CATLASS_DEVICE
|
|
static Layout create(uint32_t k, uint32_t n) {
|
|
return Layout{k, n};
|
|
}
|
|
};
|
|
|
|
template <typename Layout, typename ElementType>
|
|
struct LayoutBInitializer<Layout, ElementType,
|
|
std::enable_if_t<std::is_same_v<Layout, layout::zN>>
|
|
> {
|
|
CATLASS_DEVICE
|
|
static Layout create(uint32_t k, uint32_t n) {
|
|
return Layout::template MakeLayout<ElementType>(k, n);
|
|
}
|
|
};
|
|
#endif // SELECT_HELPER_HPP
|